| { | |
| "best_metric": 10.368042945861816, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06562756357670221, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013125512715340443, | |
| "grad_norm": 0.03926453739404678, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013125512715340443, | |
| "eval_loss": 10.376840591430664, | |
| "eval_runtime": 0.1122, | |
| "eval_samples_per_second": 445.734, | |
| "eval_steps_per_second": 115.891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026251025430680886, | |
| "grad_norm": 0.04012450948357582, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3805, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003937653814602133, | |
| "grad_norm": 0.04312530532479286, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005250205086136177, | |
| "grad_norm": 0.04319090023636818, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006562756357670222, | |
| "grad_norm": 0.04669618606567383, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3806, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007875307629204267, | |
| "grad_norm": 0.03991042450070381, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.38, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00918785890073831, | |
| "grad_norm": 0.03521149605512619, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3762, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010500410172272354, | |
| "grad_norm": 0.039370447397232056, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3806, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011812961443806398, | |
| "grad_norm": 0.044457413256168365, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013125512715340444, | |
| "grad_norm": 0.04319475218653679, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3782, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014438063986874488, | |
| "grad_norm": 0.0448758527636528, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3779, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015750615258408533, | |
| "grad_norm": 0.05618163198232651, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3788, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017063166529942577, | |
| "grad_norm": 0.05045272037386894, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3786, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01837571780147662, | |
| "grad_norm": 0.03747754544019699, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.372, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019688269073010665, | |
| "grad_norm": 0.04165615513920784, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3792, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02100082034454471, | |
| "grad_norm": 0.045003049075603485, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3754, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022313371616078752, | |
| "grad_norm": 0.047799721360206604, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3764, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023625922887612796, | |
| "grad_norm": 0.042904093861579895, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3746, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02493847415914684, | |
| "grad_norm": 0.04932091012597084, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.026251025430680888, | |
| "grad_norm": 0.051909852772951126, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3769, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02756357670221493, | |
| "grad_norm": 0.049463506788015366, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3767, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028876127973748975, | |
| "grad_norm": 0.055745791643857956, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3731, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.055917635560035706, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3762, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031501230516817066, | |
| "grad_norm": 0.06721573323011398, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3774, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "grad_norm": 0.07637108862400055, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03281378178835111, | |
| "eval_loss": 10.371264457702637, | |
| "eval_runtime": 0.1048, | |
| "eval_samples_per_second": 477.306, | |
| "eval_steps_per_second": 124.099, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034126333059885154, | |
| "grad_norm": 0.05495060980319977, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3716, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.035438884331419195, | |
| "grad_norm": 0.05448654294013977, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3711, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03675143560295324, | |
| "grad_norm": 0.04656277596950531, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03806398687448728, | |
| "grad_norm": 0.06399563699960709, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3713, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03937653814602133, | |
| "grad_norm": 0.055098455399274826, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04068908941755537, | |
| "grad_norm": 0.0529935285449028, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3719, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04200164068908942, | |
| "grad_norm": 0.06360534578561783, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3723, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.043314191960623465, | |
| "grad_norm": 0.06396108120679855, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3751, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.044626743232157505, | |
| "grad_norm": 0.0684530958533287, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3772, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04593929450369155, | |
| "grad_norm": 0.08383864164352417, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3758, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04725184577522559, | |
| "grad_norm": 0.08766114711761475, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3777, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04856439704675964, | |
| "grad_norm": 0.08422145992517471, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3731, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04987694831829368, | |
| "grad_norm": 0.0764157697558403, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3734, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05118949958982773, | |
| "grad_norm": 0.05682424083352089, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3717, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.052502050861361775, | |
| "grad_norm": 0.0720311626791954, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3722, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053814602132895815, | |
| "grad_norm": 0.07053551822900772, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3727, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05512715340442986, | |
| "grad_norm": 0.07562316954135895, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3713, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0564397046759639, | |
| "grad_norm": 0.07481846213340759, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3691, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05775225594749795, | |
| "grad_norm": 0.07317402213811874, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3689, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05906480721903199, | |
| "grad_norm": 0.07008465379476547, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3744, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.07423053681850433, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3754, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06168990976210008, | |
| "grad_norm": 0.06752587109804153, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3708, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06300246103363413, | |
| "grad_norm": 0.0797606110572815, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3723, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06431501230516817, | |
| "grad_norm": 0.09553766995668411, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3691, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "grad_norm": 0.1018286645412445, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06562756357670221, | |
| "eval_loss": 10.368042945861816, | |
| "eval_runtime": 0.0965, | |
| "eval_samples_per_second": 518.034, | |
| "eval_steps_per_second": 134.689, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |